Method for adaptive conversation state management with filtering operators applied dynamically as part of a conversational interface

Abstract

A system and method of processing a search request is provided. Identification of a desired content item is based on comparing a topic of the search request to previous user input. The method includes providing access to a set of content items with metadata that describes the corresponding content items and providing information about previous searches. The method further includes receiving a present input from the user and determining a relatedness measure between the information about the previous searches and an element of the present input. If the relatedness measure is high, the method also includes selecting a subset of content items based on comparing the present input and information about the previous searches with the metadata that describes the subset of content items. Otherwise, the method includes selecting a subset of content items based on comparing the present input with the metadata that describes the subset of content items.

What is claimed is: 
     
       1. A method for processing search requests received from a user, the method comprising:
 providing access to a set of content items; 
 receiving a first speech input from a user; 
 selecting a first subset of the set of content items based on comparing the first speech input from the user to the set of content items; 
 generating the first subset of the set of content items for display; 
 receiving a second speech input from the user; 
 accessing a relationship database containing relationship distances between entities; 
 determining a measure of relatedness between the first speech input from a user and the second speech input from the user based on a relationship distance between a first entity corresponding to the first speech input and a second entity corresponding to the second speech input; 
 upon a condition in which the relatedness measure does not exceed a threshold value:
 selecting a second subset of the set of content items based on comparing the second speech input from the user to the set of content items; and 
 generating the second subset of the set of content items for display; and 
 
 upon a condition in which the relatedness measure exceeds the threshold value:
 selecting a third subset of the content items based on comparing the first speech input from the user and the second speech input from the user to the set of content items; and 
 generating the third subset of the set of content items for display. 
 
 
     
     
       2. The method of  claim 1 , wherein the relationship database comprises a relationship graph with nodes and edges, each node representing an entity and each edge representing a direct relationship between two entities. 
     
     
       3. The method of  claim 2 , wherein a relationship distance between two entities is measured in a smallest number of hops between two nodes corresponding to the two entities. 
     
     
       4. The method of  claim 2 , wherein each edge has a weight, and wherein a relationship distance between two entities is measured as a sum of weights of edges connecting two nodes corresponding to the two entities. 
     
     
       5. The method of  claim 1 , wherein the relationship distances in the relationship database are modified by user preferences acquired over time. 
     
     
       6. The method of  claim 1 , further comprising:
 providing access to a database containing historical inputs, wherein the relationship distances between entities are determined based on how often the entities were used together. 
 
     
     
       7. The method of  claim 1 , further comprising adjusting the threshold value based on feedback received from the user. 
     
     
       8. The method of  claim 1 , comprising:
 setting the threshold value to a first value; 
 receiving feedback input from the user indicating that the first speech input and the second speech input were improperly combined; and 
 in response to receiving the feedback input, setting the threshold value to a second value that is smaller than the first value. 
 
     
     
       9. The method of  claim 1 , further comprising:
 generating a request for the user to provide the second speech input; and 
 wherein the second speech input from the user is received in response to the request for the user to provide the second speech input. 
 
     
     
       10. A system for processing search requests received from a user, the system comprising:
 computer readable instructions encoded on a non-transitory computer readable medium, the computer readable instructions causing a computer system to:
 provide access to a set of content items; 
 receive a first speech input from a user; 
 select a first subset of the set of content items based on comparing the first speech input from the user to the set of content items; 
 generate the first subset of the set of content items for display; 
 receive a second speech input from the user; 
 access a relationship database containing relationship distances between entities; 
 determine a measure of relatedness between the first speech input from a user and the second speech input from the user based on a relationship distance between a first entity corresponding to the first speech input and a second entity corresponding to the second speech input; 
 upon a condition in which the relatedness measure does not exceed a threshold value:
 select a second subset of the set of content items based on comparing the second speech input from the user to the set of content items; and 
 generate the second subset of the set of content items for display; and 
 
 upon a condition in which the relatedness measure exceeds the threshold value:
 select a third subset of the content items based on comparing the first speech input from the user and the second speech input from the user to the set of content items; and 
 generate the third subset of the set of content items for display. 
 
 
 
     
     
       11. The system of  claim 10 , wherein the relationship database comprises a relationship graph with nodes and edges, each node representing an entity and each edge representing a direct relationship between two entities. 
     
     
       12. The system of  claim 11 , wherein a relationship distance between two entities is measured in a smallest number of hops between two nodes corresponding to the two entities. 
     
     
       13. The system of  claim 11 , wherein each edge has a weight, and wherein a relationship distance between two entities is measured as a sum of weights of edges connecting two nodes corresponding to the two entities. 
     
     
       14. The system of  claim 10 , wherein the relationship distances in the relationship database are modified by user preferences acquired over time. 
     
     
       15. The system of  claim 10 , wherein the computer readable instructions further cause the computer system to:
 provide access to a database containing historical inputs, wherein the relationship distances between entities are determined based on how often the entities were used together. 
 
     
     
       16. The system of  claim 10 , wherein the computer readable instructions further cause the computer system to adjust the threshold value based on feedback received from the user. 
     
     
       17. The system of  claim 10 , wherein the computer readable instructions further cause the computer system to:
 set the threshold value to a first value; 
 receive feedback input from the user indicating that the first speech input and the second speech input were improperly combined; and 
 in response to receiving the feedback input, set the threshold value to a second value that is smaller than the first value. 
 
     
     
       18. The system of  claim 10 , wherein the computer readable instructions further cause the computer system to:
 generate a request for the user to provide the second speech input; and 
 wherein the second speech input from the user is received in response to the request for the user to provide the second speech input.